Tensorflow variable images size within single batch

Question

I am currently implementing FCN in tensorflow that enables variable input image size.

I have images of really various image sizes, but unfortunately I am not able to start the training with batch size different than 1.

I am using the feed dict in a following way:

feed_dict = {fcn.images: image_batch,
             fcn.labels: labels_batch,
             fcn.dropout_keep: dropout}
result = sess.run(list(tf_ops), feed_dict=feed_dict)

I have already tried:

1. Creating image_batch and labels_batch as numpy array, this however does not work since numpy arrays does not support variable certain dimensions.
2. Creating image_batch and labels_batch as list of numpy arrays. Here seems that tensorflow is trying to call numpy.array(image_batch).
3. Going with tf.pack(), this unfortunately does not support different image sizes as well

My question is: Is there a way how to solve this problem?

Thank you in advance for any suggestions and advices.

Answer 1

So we can close this - quoting Olivier Moindrot above:

You have to pad or resize all your images to the same size before batching them.

Note that after Olivier's answer, there was a new tf.image.decode_and_crop_jpeg op added that can make it a bit easier to do this.